Machine Learning With Python From MIT on edX
Written by Sue Gee   
Wednesday, 26 June 2019

A free online course that brings together the most popular programming language with one of today's hottest topics has just started and you can still enroll with plenty of time to complete it.

mitx

The combination of Python with machine learning is neither surprising nor a co-incidence. Python is widely acknowledged as the most suitable programming language for this sphere and this courses sets out to be an in-depth introduction to the field of machine learning, from linear models to deep learning and reinforcement learning, through hands-on Python projects.

The full title of the course is Machine Learning with Python: from Linear Models to Deep Learning. While it can be studied as a standalone course, or in conjunction with other courses, it is the fourth course in the MITx MicroMasters Statistics and Data Science, which we outlined in a news item a year ago when it began.

The Machine Learning course lasts 13 weeks (ending on September 4, 2019) and, like the others in the program, requires 10 to 14 hours per week. It is at advanced level. For starters you need college level calculus, vectors and matrices. You also are expected to have familiarity with Python, which can be met by taking the 9-week course Introduction to Computer Science and Programming Using Python, also from MIT on edX and which started on June 5 and ends August 7. You also need a good grasp of Probability Theory - and the MITx course for this is Probability - The Science of Uncertainty and Data, and is the first of the courses in the MicroMasters program. So, while you can tackle the four courses in the program in any order, if you intend to do them all this is the best starting point. A presentation started on May 20, 2019 and runs until September 14 and the next on starts in January 2020.

In Machine Learning with Python: from Linear Models to Deep Learning students will:

  • Understand principles behind machine learning problems such as classification, regression, clustering, and reinforcement learning
  • Implement and analyze models such as linear models, kernel machines, neural networks, and graphical models
  • Choose suitable models for different applications
  • Implement and organize machine learning projects, from training, validation, parameter tuning, to feature engineering.
It comprises the following lectures and projects:
Lectures:
  • Introduction
  • Linear classifiers, separability, perceptron algorithm
  • Maximum margin hyperplane, loss, regularization
  • Stochastic gradient descent, over-fitting, generalization
  • Linear regression
  • Recommender problems, collaborative filtering
  • Non-linear classification, kernels
  • Learning features, Neural networks
  • Deep learning, back propagation
  • Recurrent neural networks
  • Recurrent neural networks
  • Generalization, complexity, VC-dimension
  • Unsupervised learning: clustering
  • Generative models, mixtures
  • Mixtures and the EM algorithm
  • Learning to control: Reinforcement learning
  • Reinforcement learning continued
  • Applications: Natural Language Processing
Projects:
  • Automatic Review Analyzer
  • Digit Recognition with Neural Networks
  • Reinforcement Learning

This seems to be a well-thought out syllabus and is claimed to be at a similar pace and level of vigor as an on-campus course at  MIT. You can follow along the course for free (without access to graded exams), but if you want to earn the MicroMaster's credential, which also involves a proctored exam once you have successfully completed all four courses, you'll need to pay $300 per course and for the Capstone exam. You can save 10% ($1,350 instead of $1,500) by paying for the MicroMasters Program, which is to be completed all within a year, at the outset. As this is a credential that will to help you into a new job or advance your career without having to stop work to study, many will find this an attractive option.

 


sdsml

 

More Information

Machine Learning with Python: from Linear Models to Deep Learning

MITx MicroMasters Statistics and Data Science  

Related Articles

Statistics & Data Science MicroMasters on edX

Coursera's Machine Learning Specialization

Free Machine Learning Training From Amazon

More Machine Learning Courses From Google

What is a Data Scientist and How Do I Become One?

 

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

 

Banner

CSS Ecosystem In the Spotlight
06/11/2024

The 2024 edition of the State of CSS has been posted, revealing that the latest features of the language not only do away with extra tooling, but even start taking on tasks that previously requir [ ... ]


+ Full Story
Flutter Forked As Flock
05/11/2024

One of developers who worked on the Flutter team at Google has created an open-source form of the framework. Matt Carroll says Flock will be "Flutter+", will remain constantly up to date with Flutter, [ ... ]


+ Full Story
More News

espbook

 

Comments




or email your comment to: comments@i-programmer.info
Last Updated ( Wednesday, 26 June 2019 )